moses-smt/mosesdecoder
1
1
Fork 0
mirror of https://github.com/moses-smt/mosesdecoder.git synced 2024-08-17 07:20:48 +03:00
Code Issues Packages Projects Releases Wiki Activity

daily automatic beautifier

Browse Source
This commit is contained in:
MosesAdmin 2016-06-02 00:00:39 +01:00
parent 2ad1eacef7
commit ea306f62b7
9 changed files with 606 additions and 597 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
mert/M2.cpp
View File

@ -3,21 +3,23 @@
#include "M2.h"
namespace MosesTuning {
namespace MosesTuning
{
namespace M2 {
namespace M2
{
bool Annot::lowercase = true;
std::string Annot::transform(const std::string& e) {
std::string temp = e;
if(lowercase) {
boost::erase_all(temp, " ");
return ToLower(temp);
}
else
return e;
}
std::string Annot::transform(const std::string& e)
{
std::string temp = e;
if(lowercase) {
boost::erase_all(temp, " ");
return ToLower(temp);
} else
return e;
}
const std::string ToLower(const std::string& str)
{
@ -27,27 +29,30 @@ const std::string ToLower(const std::string& str)
}
Edit operator+(Edit& e1, Edit& e2) {
std::string edit;
if(e1.edit.size() > 0 && e2.edit.size() > 0)
edit = e1.edit + " " + e2.edit;
else if(e1.edit.size() > 0)
edit = e1.edit;
else if(e2.edit.size() > 0)
edit = e2.edit;
Edit operator+(Edit& e1, Edit& e2)
{
std::string edit;
if(e1.edit.size() > 0 && e2.edit.size() > 0)
edit = e1.edit + " " + e2.edit;
else if(e1.edit.size() > 0)
edit = e1.edit;
else if(e2.edit.size() > 0)
edit = e2.edit;
return Edit(e1.cost + e2.cost, e1.changed + e2.changed, e1.unchanged + e2.unchanged, edit);
return Edit(e1.cost + e2.cost, e1.changed + e2.changed, e1.unchanged + e2.unchanged, edit);
}
Edge operator+(Edge e1, Edge e2) {
return Edge(e1.v, e2.u, e1.edit + e2.edit);
Edge operator+(Edge e1, Edge e2)
{
return Edge(e1.v, e2.u, e1.edit + e2.edit);
}
std::ostream& operator<<(std::ostream& o, Sentence s) {
for(Sentence::iterator it = s.begin(); it != s.end(); it++)
o << *it << " ";
return o;
std::ostream& operator<<(std::ostream& o, Sentence s)
{
for(Sentence::iterator it = s.begin(); it != s.end(); it++)
o << *it << " ";
return o;
}

664
mert/M2.h
View File

@ -16,9 +16,11 @@
namespace MosesTuning {
namespace MosesTuning
{
namespace M2 {
namespace M2
{
typedef std::vector<float> Stats;
@ -29,43 +31,43 @@ std::ostream& operator<<(std::ostream& o, Sentence s);
const std::string ToLower(const std::string& str);
struct Annot {
size_t i;
size_t j;
size_t i;
size_t j;
std::string type;
std::string edit;
std::string type;
std::string edit;
size_t annotator;
size_t annotator;
bool operator<(Annot a) const {
return i < a.i || (i == a.i && j < a.j)
|| (i == a.i && j == a.j && annotator < a.annotator)
|| (i == a.i && j == a.j && annotator == a.annotator && transform(edit) < transform(a.edit));
}
bool operator<(Annot a) const {
return i < a.i || (i == a.i && j < a.j)
|| (i == a.i && j == a.j && annotator < a.annotator)
|| (i == a.i && j == a.j && annotator == a.annotator && transform(edit) < transform(a.edit));
}
bool operator==(Annot a) const {
return (!(*this < a) && !(a < *this));
}
bool operator==(Annot a) const {
return (!(*this < a) && !(a < *this));
}
static std::string transform(const std::string& e);
static std::string transform(const std::string& e);
static bool lowercase;
static bool lowercase;
};
typedef std::set<Annot> Annots;
typedef std::set<size_t> Users;
struct Unit {
Sentence first;
Annots second;
Users third;
Sentence first;
Annots second;
Users third;
};
typedef std::vector<Unit> M2File;
struct Edit {
Edit(float c = 1.0, size_t ch = 0, size_t unch = 1, std::string e = "")
: cost(c), changed(ch), unchanged(unch), edit(e) {}
: cost(c), changed(ch), unchanged(unch), edit(e) {}
float cost;
size_t changed;
@ -92,7 +94,7 @@ struct Vertex {
struct Edge {
Edge(Vertex vv = Vertex(), Vertex uu = Vertex(), Edit editt = Edit())
: v(vv), u(uu), edit(editt) {}
: v(vv), u(uu), edit(editt) {}
bool operator<(const Edge &e) const {
return v < e.v || (v == e.v && u < e.u);
@ -110,7 +112,7 @@ typedef std::vector<Row> Matrix;
struct Info {
Info(Vertex vv = Vertex(), Edit editt = Edit())
: v(vv), edit(editt) {}
: v(vv), edit(editt) {}
bool operator<(const Info &i) const {
return v < i.v;
@ -127,352 +129,350 @@ typedef std::vector<TrackRow> TrackMatrix;
typedef std::set<Vertex> Vertices;
typedef std::set<Edge> Edges;
class M2 {
private:
M2File m_m2;
class M2
{
private:
M2File m_m2;
size_t m_max_unchanged;
float m_beta;
bool m_lowercase;
bool m_verbose;
size_t m_max_unchanged;
float m_beta;
bool m_lowercase;
bool m_verbose;
public:
M2() : m_max_unchanged(2), m_beta(0.5), m_lowercase(true), m_verbose(false) { }
M2(size_t max_unchanged, float beta, bool truecase, bool verbose = false)
public:
M2() : m_max_unchanged(2), m_beta(0.5), m_lowercase(true), m_verbose(false) { }
M2(size_t max_unchanged, float beta, bool truecase, bool verbose = false)
: m_max_unchanged(max_unchanged), m_beta(beta), m_lowercase(!truecase), m_verbose(verbose) {
if(!m_lowercase) {
Annot::lowercase = false;
}
if(!m_lowercase) {
Annot::lowercase = false;
}
}
float Beta() {
return m_beta;
}
float Beta() {
return m_beta;
}
void ReadM2(const std::string& filename) {
std::ifstream m2file(filename.c_str());
std::string line;
void ReadM2(const std::string& filename) {
std::ifstream m2file(filename.c_str());
std::string line;
Unit unit;
bool first = true;
Unit unit;
bool first = true;
while(std::getline(m2file, line)) {
if(line.size() > 2) {
if(line.substr(0, 2) == "S ") {
if(!first) {
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
first = false;
while(std::getline(m2file, line)) {
if(line.size() > 2) {
if(line.substr(0, 2) == "S ") {
if(!first) {
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
first = false;
unit.first = Sentence();
unit.second = Annots();
unit.first = Sentence();
unit.second = Annots();
std::string sentenceLine = line.substr(2);
boost::split(unit.first, sentenceLine, boost::is_any_of(" "), boost::token_compress_on);
}
if(line.substr(0, 2) == "A ") {
std::string annotLine = line.substr(2);
std::vector<std::string> annot;
boost::iter_split(annot, annotLine, boost::algorithm::first_finder("|||"));
if(annot[1] != "noop") {
Annot a;
std::stringstream rangeStr(annot[0]);
rangeStr >> a.i >> a.j;
a.type = annot[1];
a.edit = annot[2];
std::stringstream annotStr(annot[5]);
annotStr >> a.annotator;
unit.third.insert(a.annotator);
unit.second.insert(a);
}
else {
std::stringstream annotStr(annot[5]);
size_t annotator;
annotStr >> annotator;
unit.third.insert(annotator);
}
}
}
std::string sentenceLine = line.substr(2);
boost::split(unit.first, sentenceLine, boost::is_any_of(" "), boost::token_compress_on);
}
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
if(line.substr(0, 2) == "A ") {
std::string annotLine = line.substr(2);
size_t LevenshteinMatrix(const Sentence &s1, const Sentence &s2, Matrix &d, TrackMatrix &bt) {
size_t n = s1.size();
size_t m = s2.size();
std::vector<std::string> annot;
boost::iter_split(annot, annotLine, boost::algorithm::first_finder("|||"));
if (n == 0)
return m;
if (m == 0)
return n;
if(annot[1] != "noop") {
Annot a;
std::stringstream rangeStr(annot[0]);
rangeStr >> a.i >> a.j;
a.type = annot[1];
a.edit = annot[2];
d.resize(n + 1, Row(m + 1, 0));
bt.resize(n + 1, TrackRow(m + 1));
std::stringstream annotStr(annot[5]);
annotStr >> a.annotator;
for(size_t i = 0; i <= n; ++i) {
d[i][0] = i;
if(i > 0)
bt[i][0].insert(Info(Vertex(i - 1, 0), Edit(1, 1, 0, "")));
}
for(size_t j = 0; j <= m; ++j) {
d[0][j] = j;
if(j > 0)
bt[0][j].insert(Info(Vertex(0, j - 1), Edit(1, 1, 0, s2[j - 1])));
}
int cost;
for(size_t i = 1; i <= n; ++i) {
for(size_t j = 1; j <= m; ++j) {
if(Annot::transform(s1[i-1]) == Annot::transform(s2[j-1]))
cost = 0;
else
cost = 2;
size_t left = d[i][j - 1] + 1;
size_t down = d[i - 1][j] + 1;
size_t diag = d[i - 1][j - 1] + cost;
d[i][j] = std::min(left, std::min(down, diag));
if(d[i][j] == left)
bt[i][j].insert(Info(Vertex(i, j - 1), Edit(1, 1, 0, s2[j - 1])));
if(d[i][j] == down)
bt[i][j].insert(Info(Vertex(i - 1, j), Edit(1, 1, 0, "")));
if(d[i][j] == diag)
bt[i][j].insert(Info(Vertex(i - 1, j - 1), cost ? Edit(1, 1, 0, s2[j - 1]) : Edit(1, 0, 1, s2[j - 1]) ));
unit.third.insert(a.annotator);
unit.second.insert(a);
} else {
std::stringstream annotStr(annot[5]);
size_t annotator;
annotStr >> annotator;
unit.third.insert(annotator);
}
}
return d[n][m];
}
}
if(unit.third.empty())
unit.third.insert(0);
m_m2.push_back(unit);
}
size_t LevenshteinMatrix(const Sentence &s1, const Sentence &s2, Matrix &d, TrackMatrix &bt) {
size_t n = s1.size();
size_t m = s2.size();
if (n == 0)
return m;
if (m == 0)
return n;
d.resize(n + 1, Row(m + 1, 0));
bt.resize(n + 1, TrackRow(m + 1));
for(size_t i = 0; i <= n; ++i) {
d[i][0] = i;
if(i > 0)
bt[i][0].insert(Info(Vertex(i - 1, 0), Edit(1, 1, 0, "")));
}
for(size_t j = 0; j <= m; ++j) {
d[0][j] = j;
if(j > 0)
bt[0][j].insert(Info(Vertex(0, j - 1), Edit(1, 1, 0, s2[j - 1])));
}
int cost;
for(size_t i = 1; i <= n; ++i) {
for(size_t j = 1; j <= m; ++j) {
if(Annot::transform(s1[i-1]) == Annot::transform(s2[j-1]))
cost = 0;
else
cost = 2;
void BuildGraph(const TrackMatrix &bt, Vertices &V, Edges &E) {
Vertex start(bt.size() - 1, bt[0].size() - 1);
size_t left = d[i][j - 1] + 1;
size_t down = d[i - 1][j] + 1;
size_t diag = d[i - 1][j - 1] + cost;
std::queue<Vertex> Q;
Q.push(start);
while(!Q.empty()) {
Vertex v = Q.front();
Q.pop();
if(V.count(v) > 0)
continue;
V.insert(v);
for(Track::iterator it = bt[v.i][v.j].begin();
it != bt[v.i][v.j].end(); ++it) {
Edge e(it->v, v, it->edit);
E.insert(e);
if(V.count(e.v) == 0)
Q.push(e.v);
}
}
d[i][j] = std::min(left, std::min(down, diag));
Edges newE;
do {
newE.clear();
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
for(Edges::iterator it2 = E.begin(); it2 != E.end(); ++it2) {
if(it1->u == it2->v) {
Edge e = *it1 + *it2;
if(e.edit.changed > 0 &&
e.edit.unchanged <= m_max_unchanged &&
E.count(e) == 0)
newE.insert(e);
}
}
}
E.insert(newE.begin(), newE.end());
} while(newE.size() > 0);
if(d[i][j] == left)
bt[i][j].insert(Info(Vertex(i, j - 1), Edit(1, 1, 0, s2[j - 1])));
if(d[i][j] == down)
bt[i][j].insert(Info(Vertex(i - 1, j), Edit(1, 1, 0, "")));
if(d[i][j] == diag)
bt[i][j].insert(Info(Vertex(i - 1, j - 1), cost ? Edit(1, 1, 0, s2[j - 1]) : Edit(1, 0, 1, s2[j - 1]) ));
}
}
return d[n][m];
}
void BuildGraph(const TrackMatrix &bt, Vertices &V, Edges &E) {
Vertex start(bt.size() - 1, bt[0].size() - 1);
std::queue<Vertex> Q;
Q.push(start);
while(!Q.empty()) {
Vertex v = Q.front();
Q.pop();
if(V.count(v) > 0)
continue;
V.insert(v);
for(Track::iterator it = bt[v.i][v.j].begin();
it != bt[v.i][v.j].end(); ++it) {
Edge e(it->v, v, it->edit);
E.insert(e);
if(V.count(e.v) == 0)
Q.push(e.v);
}
}
void AddWeights(Edges &E, const Unit &u, size_t aid) {
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
if(it1->edit.changed > 0) {
const_cast<float&>(it1->edit.cost) += 0.001;
for(Annots::iterator it2 = u.second.begin(); it2 != u.second.end(); ++it2) {
// if matches an annotator
if(it1->v.i == it2->i && it1->u.i == it2->j
&& Annot::transform(it1->edit.edit) == Annot::transform(it2->edit)
&& it2->annotator == aid) {
int newWeight = -(m_max_unchanged + 1) * E.size();
const_cast<float&>(it1->edit.cost) = newWeight;
}
}
}
}
}
void BellmanFord(Vertices &V, Edges &E) {
Vertex source(0, 0);
std::map<Vertex, float> distance;
std::map<Vertex, Vertex> predecessor;
for(Vertices::iterator it = V.begin(); it != V.end(); ++it) {
if(*it == source)
distance[*it] = 0;
else {
distance[*it] = std::numeric_limits<float>::infinity();
}
}
for(size_t i = 1; i < V.size(); ++i) {
for(Edges::iterator it = E.begin(); it != E.end(); ++it) {
if(distance[it->v] + it->edit.cost < distance[it->u]) {
distance[it->u] = distance[it->v] + it->edit.cost;
predecessor[it->u] = it->v;
}
}
}
Edges newE;
Vertex v = *V.rbegin();
while(true) {
//std::cout << predecessor[v] << " -> " << v << std::endl;
Edges::iterator it = E.find(Edge(predecessor[v], v));
if(it != E.end()) {
Edge f = *it;
//std::cout << f << std::endl;
newE.insert(f);
v = predecessor[v];
if(v == source)
break;
}
else {
std::cout << "Error" << std::endl;
break;
}
}
E.clear();
E.insert(newE.begin(), newE.end());
}
void AddStats(const std::vector<Edges> &Es, const Unit &u, Stats &stats, size_t line) {
std::map<size_t, Stats> statsPerAnnotator;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
statsPerAnnotator[*it] = Stats(4, 0);
}
for(Annots::iterator it = u.second.begin(); it != u.second.end(); it++)
statsPerAnnotator[it->annotator][2]++;
for(std::set<size_t>::iterator ait = u.third.begin();
ait != u.third.end(); ++ait) {
for(Edges::iterator eit = Es[*ait].begin(); eit != Es[*ait].end(); ++eit) {
if(eit->edit.changed > 0) {
statsPerAnnotator[*ait][1]++;
Annot f;
f.i = eit->v.i;
f.j = eit->u.i;
f.annotator = *ait;
f.edit = eit->edit.edit;
for(Annots::iterator fit = u.second.begin(); fit != u.second.end(); fit++) {
if(f == *fit)
statsPerAnnotator[*ait][0]++;
}
}
Edges newE;
do {
newE.clear();
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
for(Edges::iterator it2 = E.begin(); it2 != E.end(); ++it2) {
if(it1->u == it2->v) {
Edge e = *it1 + *it2;
if(e.edit.changed > 0 &&
e.edit.unchanged <= m_max_unchanged &&
E.count(e) == 0)
newE.insert(e);
}
}
size_t bestAnnot = 0;
float bestF = -1;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
Stats localStats = stats;
localStats[0] += statsPerAnnotator[*it][0];
localStats[1] += statsPerAnnotator[*it][1];
localStats[2] += statsPerAnnotator[*it][2];
if(m_verbose)
std::cerr << *it << " : " << localStats[0] << " " << localStats[1] << " " << localStats[2] << std::endl;
float f = FScore(localStats);
if(m_verbose)
std::cerr << f << std::endl;
if(f > bestF) {
bestF = f;
bestAnnot = *it;
}
}
E.insert(newE.begin(), newE.end());
} while(newE.size() > 0);
}
void AddWeights(Edges &E, const Unit &u, size_t aid) {
for(Edges::iterator it1 = E.begin(); it1 != E.end(); ++it1) {
if(it1->edit.changed > 0) {
const_cast<float&>(it1->edit.cost) += 0.001;
for(Annots::iterator it2 = u.second.begin(); it2 != u.second.end(); ++it2) {
// if matches an annotator
if(it1->v.i == it2->i && it1->u.i == it2->j
&& Annot::transform(it1->edit.edit) == Annot::transform(it2->edit)
&& it2->annotator == aid) {
int newWeight = -(m_max_unchanged + 1) * E.size();
const_cast<float&>(it1->edit.cost) = newWeight;
}
}
if(m_verbose)
std::cerr << ">> Chosen Annotator for line " << line + 1 << " : " << bestAnnot << std::endl;
stats[0] += statsPerAnnotator[bestAnnot][0];
stats[1] += statsPerAnnotator[bestAnnot][1];
stats[2] += statsPerAnnotator[bestAnnot][2];
}
}
}
void BellmanFord(Vertices &V, Edges &E) {
Vertex source(0, 0);
std::map<Vertex, float> distance;
std::map<Vertex, Vertex> predecessor;
for(Vertices::iterator it = V.begin(); it != V.end(); ++it) {
if(*it == source)
distance[*it] = 0;
else {
distance[*it] = std::numeric_limits<float>::infinity();
}
}
void SufStats(const std::string &sStr, size_t i, Stats &stats) {
std::string temp = sStr;
Sentence s;
boost::split(s, temp, boost::is_any_of(" "), boost::token_compress_on);
Unit &unit = m_m2[i];
Matrix d;
TrackMatrix bt;
size_t distance = LevenshteinMatrix(unit.first, s, d, bt);
std::vector<Vertices> Vs(unit.third.size());
std::vector<Edges> Es(unit.third.size());
if(distance > unit.first.size()) {
std::cerr << "Levenshtein distance is greater than source size." << std::endl;
stats[0] = 0;
stats[1] = distance;
stats[2] = 0;
stats[3] = unit.first.size();
return;
for(size_t i = 1; i < V.size(); ++i) {
for(Edges::iterator it = E.begin(); it != E.end(); ++it) {
if(distance[it->v] + it->edit.cost < distance[it->u]) {
distance[it->u] = distance[it->v] + it->edit.cost;
predecessor[it->u] = it->v;
}
else if(distance > 0) {
for(size_t j = 0; j < unit.third.size(); j++) {
BuildGraph(bt, Vs[j], Es[j]);
AddWeights(Es[j], unit, j);
BellmanFord(Vs[j], Es[j]);
}
}
}
Edges newE;
Vertex v = *V.rbegin();
while(true) {
//std::cout << predecessor[v] << " -> " << v << std::endl;
Edges::iterator it = E.find(Edge(predecessor[v], v));
if(it != E.end()) {
Edge f = *it;
//std::cout << f << std::endl;
newE.insert(f);
v = predecessor[v];
if(v == source)
break;
} else {
std::cout << "Error" << std::endl;
break;
}
}
E.clear();
E.insert(newE.begin(), newE.end());
}
void AddStats(const std::vector<Edges> &Es, const Unit &u, Stats &stats, size_t line) {
std::map<size_t, Stats> statsPerAnnotator;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
statsPerAnnotator[*it] = Stats(4, 0);
}
for(Annots::iterator it = u.second.begin(); it != u.second.end(); it++)
statsPerAnnotator[it->annotator][2]++;
for(std::set<size_t>::iterator ait = u.third.begin();
ait != u.third.end(); ++ait) {
for(Edges::iterator eit = Es[*ait].begin(); eit != Es[*ait].end(); ++eit) {
if(eit->edit.changed > 0) {
statsPerAnnotator[*ait][1]++;
Annot f;
f.i = eit->v.i;
f.j = eit->u.i;
f.annotator = *ait;
f.edit = eit->edit.edit;
for(Annots::iterator fit = u.second.begin(); fit != u.second.end(); fit++) {
if(f == *fit)
statsPerAnnotator[*ait][0]++;
}
}
AddStats(Es, unit, stats, i);
stats[3] = unit.first.size();
}
}
float FScore(const Stats& stats) {
float p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
float r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
float denom = (m_beta * m_beta * p + r);
float f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
return f;
size_t bestAnnot = 0;
float bestF = -1;
for(std::set<size_t>::iterator it = u.third.begin();
it != u.third.end(); ++it) {
Stats localStats = stats;
localStats[0] += statsPerAnnotator[*it][0];
localStats[1] += statsPerAnnotator[*it][1];
localStats[2] += statsPerAnnotator[*it][2];
if(m_verbose)
std::cerr << *it << " : " << localStats[0] << " " << localStats[1] << " " << localStats[2] << std::endl;
float f = FScore(localStats);
if(m_verbose)
std::cerr << f << std::endl;
if(f > bestF) {
bestF = f;
bestAnnot = *it;
}
}
if(m_verbose)
std::cerr << ">> Chosen Annotator for line " << line + 1 << " : " << bestAnnot << std::endl;
stats[0] += statsPerAnnotator[bestAnnot][0];
stats[1] += statsPerAnnotator[bestAnnot][1];
stats[2] += statsPerAnnotator[bestAnnot][2];
}
void FScore(const Stats& stats, float &p, float &r, float &f) {
p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
void SufStats(const std::string &sStr, size_t i, Stats &stats) {
std::string temp = sStr;
r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
Sentence s;
boost::split(s, temp, boost::is_any_of(" "), boost::token_compress_on);
float denom = (m_beta * m_beta * p + r);
f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
Unit &unit = m_m2[i];
Matrix d;
TrackMatrix bt;
size_t distance = LevenshteinMatrix(unit.first, s, d, bt);
std::vector<Vertices> Vs(unit.third.size());
std::vector<Edges> Es(unit.third.size());
if(distance > unit.first.size()) {
std::cerr << "Levenshtein distance is greater than source size." << std::endl;
stats[0] = 0;
stats[1] = distance;
stats[2] = 0;
stats[3] = unit.first.size();
return;
} else if(distance > 0) {
for(size_t j = 0; j < unit.third.size(); j++) {
BuildGraph(bt, Vs[j], Es[j]);
AddWeights(Es[j], unit, j);
BellmanFord(Vs[j], Es[j]);
}
}
AddStats(Es, unit, stats, i);
stats[3] = unit.first.size();
}
float FScore(const Stats& stats) {
float p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
float r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
float denom = (m_beta * m_beta * p + r);
float f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
return f;
}
void FScore(const Stats& stats, float &p, float &r, float &f) {
p = 1.0;
if(stats[1] != 0)
p = (float)stats[0] / (float)stats[1];
r = 1.0;
if(stats[2] != 0)
r = (float)stats[0] / (float)stats[2];
float denom = (m_beta * m_beta * p + r);
f = 0.0;
if(denom != 0)
f = ((1 + m_beta * m_beta) * p * r) / denom;
}
};
}

6
mert/M2Scorer.cpp
View File

@ -78,11 +78,13 @@ float M2Scorer::calculateScore(const vector<ScoreStatsType>& comps) const
return f;
}
float M2Scorer::getReferenceLength(const vector<ScoreStatsType>& comps) const {
float M2Scorer::getReferenceLength(const vector<ScoreStatsType>& comps) const
{
return comps[3];
}
std::vector<ScoreStatsType> randomStats(float decay, int max) {
std::vector<ScoreStatsType> randomStats(float decay, int max)
{
int gold = rand() % max;
int prop = rand() % max;
int corr = 0.0;

95
moses/FF/CorrectionPattern.cpp
View File

@ -23,7 +23,8 @@ namespace Moses
using namespace std;
std::string MakePair(const std::string &s1, const std::string &s2, bool general) {
std::string MakePair(const std::string &s1, const std::string &s2, bool general)
{
std::vector<std::string> sourceList;
std::vector<std::string> targetList;
@ -54,27 +55,23 @@ std::string MakePair(const std::string &s1, const std::string &s2, bool general)
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\" + temp + "·");
count++;
}
else {
} else {
sourceList.push_back(match + "·");
targetList.push_back(match + "·");
}
match.clear();
}
else
} else
match.push_back(s1[i]);
i++;
j++;
}
else if(type == 'd') {
} else if(type == 'd') {
if(s1[i] == '+')
source += "·";
else
source.push_back(s1[i]);
i++;
}
else if(type == 'i') {
} else if(type == 'i') {
if(s2[j] == '+')
target += "·";
else
@ -88,8 +85,7 @@ std::string MakePair(const std::string &s1, const std::string &s2, bool general)
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\" + temp);
count++;
}
else {
} else {
sourceList.push_back(match);
targetList.push_back(match);
}
@ -111,15 +107,13 @@ std::string MakePair(const std::string &s1, const std::string &s2, bool general)
sprintf((char*)temp.c_str(), "%d", count);
targetList.push_back("\\"+ temp);
count++;
}
else {
} else {
sourceList.push_back(match);
targetList.push_back(match);
}
}
match.clear();
}
else {
} else {
std::string cs1 = s1;
std::string cs2 = s2;
boost::replace_all(cs1, "+", "·");
@ -139,17 +133,16 @@ std::string MakePair(const std::string &s1, const std::string &s2, bool general)
return out.str();
}
std::string CorrectionPattern::CreateSinglePattern(const Tokens &s1, const Tokens &s2) const {
std::string CorrectionPattern::CreateSinglePattern(const Tokens &s1, const Tokens &s2) const
{
std::stringstream out;
if(s1.empty()) {
out << "ins(«" << boost::join(s2, "·") << "»)";
return out.str();
}
else if(s2.empty()) {
} else if(s2.empty()) {
out << "del(«" << boost::join(s1, "·") << "»)";
return out.str();
}
else {
} else {
typename Tokens::value_type v1 = boost::join(s1, "+");
typename Tokens::value_type v2 = boost::join(s2, "+");
out << MakePair(v1, v2, m_general);
@ -158,12 +151,13 @@ std::string CorrectionPattern::CreateSinglePattern(const Tokens &s1, const Token
}
std::vector<std::string> GetContext(size_t pos,
size_t len,
size_t window,
const InputType &input,
const InputPath &inputPath,
const std::vector<FactorType>& factorTypes,
bool isRight) {
size_t len,
size_t window,
const InputType &input,
const InputPath &inputPath,
const std::vector<FactorType>& factorTypes,
bool isRight)
{
const Sentence& sentence = static_cast<const Sentence&>(input);
const Range& range = inputPath.GetWordsRange();
@ -179,8 +173,7 @@ std::vector<std::string> GetContext(size_t pos,
for(int i = 0; i < length; i++) {
if(leftPos - i >= 0) {
current.push_back(sentence.GetWord(leftPos - i).GetString(factorTypes, false));
}
else {
} else {
current.push_back("<s>");
}
}
@ -195,8 +188,7 @@ std::vector<std::string> GetContext(size_t pos,
for(int i = 0; i < length; i++) {
if(rightPos + i < (int)sentence.GetSize()) {
current.push_back(sentence.GetWord(rightPos + i).GetString(factorTypes, false));
}
else {
} else {
current.push_back("</s>");
}
}
@ -214,7 +206,8 @@ std::vector<std::string>
CorrectionPattern::CreatePattern(const Tokens &s1,
const Tokens &s2,
const InputType &input,
const InputPath &inputPath) const {
const InputPath &inputPath) const
{
Diffs diffs = CreateDiff(s1, s2);
size_t i = 0, j = 0;
@ -232,14 +225,14 @@ CorrectionPattern::CreatePattern(const Tokens &s1,
std::vector<std::string> rightContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, true);
BOOST_FOREACH(std::string left, leftContexts)
patternList.push_back(left + pattern);
patternList.push_back(left + pattern);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(pattern + right);
patternList.push_back(pattern + right);
BOOST_FOREACH(std::string left, leftContexts)
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
}
}
source.clear();
@ -250,12 +243,10 @@ CorrectionPattern::CreatePattern(const Tokens &s1,
}
i++;
j++;
}
else if(type == 'd') {
} else if(type == 'd') {
source.push_back(s1[i]);
i++;
}
else if(type == 'i') {
} else if(type == 'i') {
target.push_back(s2[j]);
j++;
}
@ -270,14 +261,14 @@ CorrectionPattern::CreatePattern(const Tokens &s1,
std::vector<std::string> rightContexts = GetContext(i, source.size(), m_context, input, inputPath, m_contextFactors, true);
BOOST_FOREACH(std::string left, leftContexts)
patternList.push_back(left + pattern);
patternList.push_back(left + pattern);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(pattern + right);
patternList.push_back(pattern + right);
BOOST_FOREACH(std::string left, leftContexts)
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
BOOST_FOREACH(std::string right, rightContexts)
patternList.push_back(left + pattern + right);
}
}
@ -308,20 +299,20 @@ void CorrectionPattern::SetParameter(const std::string& key, const std::string&
}
void CorrectionPattern::EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore) const
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore) const
{
ComputeFeatures(input, inputPath, targetPhrase, &scoreBreakdown);
}
void CorrectionPattern::ComputeFeatures(
const InputType &input,
const InputPath &inputPath,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
const InputType &input,
const InputPath &inputPath,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
{
const Phrase &source = inputPath.GetPhrase();

22
moses/FF/CorrectionPattern.h
View File

@ -29,27 +29,27 @@ public:
bool IsUseable(const FactorMask &mask) const;
void EvaluateInIsolation(const Phrase &source
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
{}
virtual void EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const;
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const;
void EvaluateTranslationOptionListWithSourceContext(const InputType &input
, const TranslationOptionList &translationOptionList) const
, const TranslationOptionList &translationOptionList) const
{}
void EvaluateWhenApplied(const Hypothesis& hypo,
ScoreComponentCollection* accumulator) const
ScoreComponentCollection* accumulator) const
{}
void EvaluateWhenApplied(const ChartHypothesis &hypo,
ScoreComponentCollection* accumulator) const
ScoreComponentCollection* accumulator) const
{}
void ComputeFeatures(const InputType &input,

73
moses/FF/Diffs.h
View File

@ -11,22 +11,21 @@ typedef std::vector<Diff> Diffs;
template <class Sequence, class Pred>
void CreateDiffRec(size_t** c,
const Sequence &s1,
const Sequence &s2,
size_t start,
size_t i,
size_t j,
Diffs& diffs,
Pred pred) {
const Sequence &s1,
const Sequence &s2,
size_t start,
size_t i,
size_t j,
Diffs& diffs,
Pred pred)
{
if(i > 0 && j > 0 && pred(s1[i - 1 + start], s2[j - 1 + start])) {
CreateDiffRec(c, s1, s2, start, i - 1, j - 1, diffs, pred);
diffs.push_back(Diff('m'));
}
else if(j > 0 && (i == 0 || c[i][j-1] >= c[i-1][j])) {
} else if(j > 0 && (i == 0 || c[i][j-1] >= c[i-1][j])) {
CreateDiffRec(c, s1, s2, start, i, j-1, diffs, pred);
diffs.push_back(Diff('i'));
}
else if(i > 0 && (j == 0 || c[i][j-1] < c[i-1][j])) {
} else if(i > 0 && (j == 0 || c[i][j-1] < c[i-1][j])) {
CreateDiffRec(c, s1, s2, start, i-1, j, diffs, pred);
diffs.push_back(Diff('d'));
}
@ -34,8 +33,9 @@ void CreateDiffRec(size_t** c,
template <class Sequence, class Pred>
Diffs CreateDiff(const Sequence& s1,
const Sequence& s2,
Pred pred) {
const Sequence& s2,
Pred pred)
{
Diffs diffs;
@ -84,12 +84,14 @@ Diffs CreateDiff(const Sequence& s1,
}
template <class Sequence>
Diffs CreateDiff(const Sequence& s1, const Sequence& s2) {
Diffs CreateDiff(const Sequence& s1, const Sequence& s2)
{
return CreateDiff(s1, s2, std::equal_to<typename Sequence::value_type>());
}
template <class Sequence, class Sig, class Stats>
void AddStats(const Sequence& s1, const Sequence& s2, const Sig& sig, Stats& stats) {
void AddStats(const Sequence& s1, const Sequence& s2, const Sig& sig, Stats& stats)
{
if(sig.size() != stats.size())
throw "Signature size differs from score array size.";
@ -109,27 +111,36 @@ void AddStats(const Sequence& s1, const Sequence& s2, const Sig& sig, Stats& sta
k++;
}
j += k;
}
else if(diff[j] == 'i')
} else if(diff[j] == 'i')
i++;
}
for(size_t j = 0; j < sig.size(); ++j) {
switch (sig[j]) {
case 'l': stats[j] += d + i + s; break;
case 'm': stats[j] += m; break;
case 'd': stats[j] += d; break;
case 'i': stats[j] += i; break;
case 's': stats[j] += s; break;
case 'r':
float macc = 1;
if (d + i + s + m)
macc = 1.0 - (float)(d + i + s)/(float)(d + i + s + m);
if(macc > 0)
stats[j] += log(macc);
else
stats[j] += log(1.0/(float)(d + i + s + m + 1));
break;
case 'l':
stats[j] += d + i + s;
break;
case 'm':
stats[j] += m;
break;
case 'd':
stats[j] += d;
break;
case 'i':
stats[j] += i;
break;
case 's':
stats[j] += s;
break;
case 'r':
float macc = 1;
if (d + i + s + m)
macc = 1.0 - (float)(d + i + s)/(float)(d + i + s + m);
if(macc > 0)
stats[j] += log(macc);
else
stats[j] += log(1.0/(float)(d + i + s + m + 1));
break;
}
}
}

20
moses/FF/EditOps.cpp
View File

@ -21,14 +21,15 @@ namespace Moses
using namespace std;
std::string ParseScores(const std::string &line, const std::string& defaultScores) {
std::string ParseScores(const std::string &line, const std::string& defaultScores)
{
std::vector<std::string> toks = Tokenize(line);
UTIL_THROW_IF2(toks.empty(), "Empty line");
for (size_t i = 1; i < toks.size(); ++i) {
std::vector<std::string> args = TokenizeFirstOnly(toks[i], "=");
UTIL_THROW_IF2(args.size() != 2,
"Incorrect format for feature function arg: " << toks[i]);
"Incorrect format for feature function arg: " << toks[i]);
if (args[0] == "scores") {
return args[1];
@ -62,17 +63,17 @@ void EditOps::Load()
{ }
void EditOps::EvaluateInIsolation(const Phrase &source
, const TargetPhrase &target
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
, const TargetPhrase &target
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const
{
ComputeFeatures(source, target, &scoreBreakdown);
}
void EditOps::ComputeFeatures(
const Phrase &source,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
const Phrase &source,
const TargetPhrase& target,
ScoreComponentCollection* accumulator) const
{
std::vector<float> ops(GetNumScoreComponents(), 0);
@ -84,8 +85,7 @@ void EditOps::ComputeFeatures(
std::string targetStr = target.GetStringRep(factors);
AddStats(sourceStr, targetStr, m_scores, ops);
}
else {
} else {
std::vector<std::string> sourceTokens;
//std::cerr << "Ed src: ";
for(size_t i = 0; i < source.GetSize(); ++i) {

22
moses/FF/EditOps.h
View File

@ -32,25 +32,25 @@ public:
void Load();
virtual void EvaluateInIsolation(const Phrase &source
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const;
, const TargetPhrase &targetPhrase
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection &estimatedFutureScore) const;
void EvaluateWithSourceContext(const InputType &input
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const
, const InputPath &inputPath
, const TargetPhrase &targetPhrase
, const StackVec *stackVec
, ScoreComponentCollection &scoreBreakdown
, ScoreComponentCollection *estimatedFutureScore = NULL) const
{}
void EvaluateWhenApplied(const Hypothesis& hypo,
ScoreComponentCollection* accumulator) const
ScoreComponentCollection* accumulator) const
{}
void EvaluateWhenApplied(const ChartHypothesis &hypo,
ScoreComponentCollection* accumulator) const
ScoreComponentCollection* accumulator) const
{}
void EvaluateTranslationOptionListWithSourceContext(const InputType &input
, const TranslationOptionList &translationOptionList) const
, const TranslationOptionList &translationOptionList) const
{}
void ComputeFeatures(const Phrase &source,